AI Paper Atlas

Research map / Detection and segmentation / CNN features

Unmixing Convolutional Features for Crisp Edge Detection

Linxi Huan, Nan Xue, Xianwei Zheng, Wei Ping He, Jianya Gong, Gui-Song Xia

TPAMI 2021 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 117 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add tracing loss and CoFusion (CATS) to RCFRCF · BSDS500 (crispness-emphasized)ODS: 0.585 -> 0.705Improved
add CATS to HEDHED · BSDS500 (crispness-emphasized)ODS: 0.588 -> 0.666Improved
add CATS to BDCNBDCN · BSDS500 (crispness-emphasized)ODS: 0.636 -> 0.696Improved
add CATS to RCFRCF · BSDS500 (standard evaluation)ODS: 0.799 -> 0.805Improved
add CATS to RCFRCF · NYUDv2 RGB (crispness-emphasized)ODS: 0.398 -> 0.474Improved
add CATS to BDCNBDCN · NYUDv2 RGB-HHA (standard evaluation)ODS: 0.766 -> 0.770Improved
add CATS to RCFRCF · Multicue EdgeODS: 0.857 -> 0.892Improved
add CATS to RCFRCF · Multicue BoundaryODS: 0.817 -> 0.841Improved
add boundary tracing function alone to RCF (ablation)RCF · NYUDv2 (crispness-emphasized)ODS: 0.381 -> 0.382No clear effect
add texture suppression function alone to RCF (ablation)RCF · NYUDv2 (crispness-emphasized)ODS: 0.381 -> 0.383No clear effect
combine boundary tracing and texture suppression (tracing loss) (ablation)RCF · NYUDv2 (crispness-emphasized)ODS: 0.381 -> 0.411Improved
add CoFusion block alone to RCF with cross entropy (ablation)RCF · NYUDv2 (crispness-emphasized)ODS: 0.381 -> 0.381No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy